The Effect of Data Augmentation on Classification of Wastes via Transfer Learning Method

Yıl 2025, Cilt: 41 Sayı: 1, 242 - 253, 30.04.2025

Necdet Tuğrul Artuğ

Öz

Effective classification of waste is one of the precautions to be taken against global warming. Carrying out this process with more practical methods instead of traditional methods, namely through artificial intelligence, will contribute to the process. In this study, classification process was conducted via transfer learning while using RealWaste dataset which contains 9 waste classes. Four different scenarios were considered to test the classification performance of the deep learning networks. Besides, the effect of data augmentation on the classification process was investigated. AlexNet, GoogLeNet, MobileNet, ResNet versions, VGG versions and Inception_v3 networks were preferred in this study. While the last 2 layers of the networks were trained, the other layers were frozen. Geometric transformations were preferred for data augmentation. The highest performance acquired without doing any additional process on the data set was 91.57% with ResNet50 network. When data augmentation was made, 99.912% classification performance was achieved with the Inception_v3 network. It was observed that data augmentation affected the classification performance in a positive way.

Anahtar Kelimeler

Waste Decomposition, Convolutional Neural Networks, Deep Learning, Transfer Learning, Artificial Intelligence

Atıkların Transfer Öğrenme Yöntemi ile Sınıflandırılmasında Veri Artırımının Etkisi

Öz

Atıkların sınıflandırılmasının efektif bir şekilde yapılması küresel ısınmaya karşı alınacak önlemlerden bir tanesidir. Bu sürecin geleneksel yöntemler yerine daha pratik yöntemlerle, yani yapay zekâ aracılığıyla yapılması sürece katkı sağlayacaktır. Bu çalışmada 9 atık sınıfı içeren RealWaste veri seti kullanılarak transfer öğrenme yoluyla sınıflandırılma işlemi gerçekleştirilmiştir. Derin öğrenme ağlarının sınıflandırma başarısının test edilmesi için dört farklı senaryo ele alınmıştır. Ayrıca veri artırımının sınıflandırma sürecine etkisi araştırılmıştır. Çalışmada AlexNet, GoogLeNet, MobileNet, ResNet serisi, VGG serisi ve Inception_v3 ağları tercih edilmiştir. Ağların son 2 katmanı eğitilirken, diğer katmanları dondurulmuştur. Veri artırımı için geometrik dönüşümler tercih edilmiştir. Veri seti üzerinde ek işlem yapılmadan en yüksek başarı %91,57 olarak ResNet50 ağıyla elde edilmiştir. Veri artırımı yapıldığında ise Inception_v3 ağıyla %99,912’lik sınıflandırma başarısı elde edilmiştir. Veri artırımının sınıflandırma başarısına pozitif etki ettiği gözlemlenmiştir.

Anahtar Kelimeler

Atık Ayrıştırma, Evrişimsel Sinir Ağları, Derin Öğrenme, Transfer Öğrenme, Yapay Zekâ

Kaynakça

• Baun, A., Jensen, S. D., Bjerg, P., Christensen, T. H., Nyholm, N. 2000. Toxicity of organic chemical pollution in groundwater downgradient of a landfill (Grindsted, Denmark). Environ. Sci. Technol., 34, 1647–1652.
• Asase, M., Yanful, E. K., Mensah, M., Stanford, J., Amponsah, S. 2009. Comparison of municipal solid waste management systems in Canada and Ghana: a case study of the cities of London, Ontario, and Kumasi, Ghana. Waste Manag., 29(10), 2779-2786.
• Themelis, N. J., Ulloa, P. A. 2006. Methane generation in landfills. Renew. Energy, 32, 1243–1257.
• Hoornweg, D., Bhada-Tata, P. 2012. What a Waste: A Global Review of Solid Waste Management. Urban development series; knowledge papers, 15. https://hdl.handle.net/10986/17388. (Erişim Tarihi: 01.02.2025).
• Mittal, G., Yagnik, K. B., Garg, M., Krishnan, N. C. 2016. Spotgarbage: smartphone app to detect garbage using deep learning. UbiComp '16: Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, 12-16 Eylül, Hamburg, 940-945.
• Chu, Y., Huang, C., Xie, X., Tan, B., Kamal, S., Xiong, X. 2018. Multilayer Hybrid Deep-Learning Method for Waste Classification and Recycling. Comput Intell Neurosci., 5060857.
• Zhang, Q., Zhang, X., Mu, X., Wang, Z., Tian, R., Wang, X., Liu, X. 2021. Recyclable waste image recognition based on deep learning. Resources, Conservation and Recycling, 171, 105636.
• Hossen, M. M., Majid, M. E., Kashem, S. B. A., Khandakar, A., Nashbat, M., Ashraf, A., Hasan-Zia, M., Kunju, A. K. A., Kabir, S., Chowdhury, M. E. 2024. A reliable and robust deep learning model for effective recyclable waste classification. IEEE Access, 12, 13809-13821.
• Oza, P., Agrawal, S., Kapadia, M., Raotole, O. 2025. Solid waste classification using deep neural network: A transfer learning approach. Earth Science Informatics, 18(2), 1-25.
• Single, S., Iranmanesh, S., Raad, R. 2023. RealWaste [Dataset]. UCI Machine Learning Repository. https://archive.ics.uci.edu/dataset/908/realwaste. (Erişim Tarihi: 14.12.2024).
• Krizhevsky, A., Sutskever, I., Hinton, G. E. 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
• Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A. 2015. Going deeper with convolutions. IEEE conference on computer vision and pattern recognition, 7-12 Haziran, Boston, 1-9.
• Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L. C. 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. IEEE conference on computer vision and pattern recognition, 18-23 Haziran, Salt Lake City, 4510-4520.
• He, K., Zhang, X., Ren, S., Sun, J. 2016. Deep residual learning for image recognition. IEEE conference on computer vision and pattern recognition, 27-30 Haziran, Las Vegas, 770-778.
• Simonyan, K., Zisserman, A. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint, arXiv:1409.1556. https://arxiv.org/abs/1409.1556. (Erişim Tarihi: 01.02.2025).
• Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z. 2016. Rethinking the inception architecture for computer vision. IEEE conference on computer vision and pattern recognition, 27-30 Haziran, Las Vegas, 2818-2826.
• de la Rosa, F. L., Gómez-Sirvent, J. L., Sánchez-Reolid, R., Morales, R., Fernández-Caballero, A. 2022. Geometric transformation-based data augmentation on defect classification of segmented images of semiconductor materials using a ResNet50 convolutional neural network. Expert Systems with Applications, 206, 117731.
• Shijie, J., Ping, W., Peiyi, J., Siping, H. 2017. Research on data augmentation for image classification based on convolution neural networks. 2017 Chinese Automation Congress (CAC), 20-22 Ekim, Çin, 4165-4170.
• Younis, H., Obaid, M. 2024. Performance Comparison of Pretrained Deep Learning Models for Landfill Waste Classification. International Journal of Advanced Computer Science & Applications, 15(11), 689-698.
• Single, S., Iranmanesh, S., Raad, R. 2023. RealWaste: A Novel Real-Life Data Set for Landfill Waste Classification Using Deep Learning. Information, 14(12), 633.
• Sharma, N., Jain, V., Mishra, A. 2018. An analysis of convolutional neural networks for image classification. Procedia computer science, 132, 377-384.